用单视图重建高分辨率扩散MRI，大幅加速扫描并突破采样限制。
Self-Supervised Spatial And Zero-Shot Angular Super-Resolution by Spatial-Angular Implicit Representation For Rotating-View SNR-Efficient Diffusion MRI
- 基于隐式神经表示，融合结构先验与扩散方向信息进行自监督重建
- 训练方向保真度达34.82 dB，未见方向重建达33.08 dB
- 适用于快速定量高分辨dMRI，尤其适合低信噪比场景
旋转视角厚层采集在介观尺度扩散MRI（dMRI）中具有高信噪比效率，但需大量旋转视角以满足奈奎斯特采样，导致扫描时间长。本文提出一种自监督的空间-角度隐式神经表示（SA-INR），可从每个扩散方向仅一个视图中重建高分辨率dMRI，实现巨大加速。模型为一个条件于b=0结构先验和b方向的MLP，通过FiLM机制实现端到端训练。该框架不仅准确重建训练过的b方向（空间超分辨率），还学习连续q空间表示，实现对未见b方向的高保真零样本合成（角度超分辨率）。在模拟数据上，训练方向重建保真度达34.82 dB，未见方向达33.08 dB。更重要的是，合成的角度数据显著提升了下游DTI模型拟合的定量准确性。SA-INR框架突破了传统采样极限，为快速、定量的高分辨率dMRI铺平道路。
原文摘要 · Abstract (English)
Rotating-view thick-slice acquisition is highly SNR-efficient for mesoscale diffusion MRI (dMRI) but requires numerous rotating views to satisfy Nyquist sampling, resulting in long scan time. We propose a self-supervised Spatial-Angular Implicit Neural Representation (SA-INR) that reconstructs high-resolution dMRI from a single view per diffusion direction, representing a massive acceleration. Our model, an MLP conditioned on a b=0 structural prior and the b-direction via FiLM, is trained end-to-end on the anisotropic input. The framework not only accurately reconstructs the trained b-directions (spatial SR) but also learns a continuous q-space representation, enabling high-fidelity "zero-shot" synthesis of unseen b-directions (angular SR). On simulated data, our method achieved high fidelity for both trained (34.82 dB) and unseen (33.08 dB) directions. Most importantly, the synthesized angular data also improved the quantitative accuracy of downstream DTI model fitting. Our SA-INR framework breaks the classical sampling limits, paving the way for fast, quantitative high-resolution dMRI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。